activity
20242026
most citedLearning to Poison Large Language Models for Downstream Manipulation

3 citations · 3 across the 5 of their papers we have counts for

collaborators
Showing 2026 · cs.LGShow all

1 paper · 2 filters

cs.LG2026

Attention Smoothing Is All You Need For Unlearning

Saleh Zare Zade, Xiangyu Zhou, Sijia Liu +1

Large Language Models are prone to memorizing sensitive, copyrighted, or hazardous content, posing significant privacy and legal concerns. Retraining from scratch is computationall…